Expired50% confidenceFactTime unknown
The single-session context windows of the latest models such as Claude and GPT-4 have expanded to 128K or more tokens, but they still cannot retain memory across sessions
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
AgentMemory: An Open-Source Solution for Giving AI Coding Assistants Permanent Memory
bilibili锋芒AI
Related Claims
Unverified128K上下文窗口意味着模型可以在单次对话中处理约6.4万汉字，早期GPT-4仅支持8K上下文81% similarVerifiedThe context windows of current mainstream large language models (such as GPT-4, Claude, etc.) have been expanded to 128K or even longer tokens.80% similarUnverifiedGPT-4's single output limit is approximately 4,096–8,192 tokens (roughly 2,000–4,000 Chinese characters), and the input context window has been expanded to 128K or even longer78% similarPartially Verified当前主流大语言模型（如GPT-4、Claude、Gemini）的上下文窗口是有限且临时的，每次对话结束后模型不会自动保留任何记忆77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/55943API
curl https://kongchang.com/api/v1/knowledge/claims/55943MCP
get_claim(id=55943)